feat: adding an option to control style of strings

Author: SGSSGene

README.rst

@@ -103,6 +103,50 @@ parses this metadata, re-applies the tags and styles, and discards the extra pai
  4 entries instead of 2. A filter that expects all array entries to be mappings may break due to the presence of string
  metadata keys. Check your jq filter for compatibility/semantic validity when using the ``-Y`` option.
 
+Forcing string styles using the ``-z`` (``--yaml-string_styles``) option
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+The ``-z`` option will assume that strings might start with some style information.
+This option is only useful when using YAML-output (using ``-y`` or ``-Y``)
+
+To control the string style, the string itself has to be prepanded by additional information.
+Valid control strings are:
+
+* ``__yq_style_'__``: uses single quotes ``'``
+* ``__yq_style_"__``: uses double quotes ``"``
+* ``__yq_style_>__`` uses ``>``, ``>`` or ``>-``, (depending on if the text has trailing break lines)
+* ``__yq_style_|__`` uses ``|``, ``|+`` or ``|-``, (depending on if the text has trailing break lines)
+
+Assume you have some input file ``input.yaml``::
+
+    field1: "I am a\nmultiline string"
+
+Example usage::
+
+    yq -y -z '.field1 |= "__yq_style_|__" + .' input.yaml
+
+This will output::
+
+    field1: |
+        I am a
+        multiline string
+
+The usage can be simplified by adding the function ``style`` to ``~/.jq`` and/or to your scripts::
+
+    # remove existing styles
+    def style: if test("^__yq_style_.__") then .[14:] | style else . end;
+
+    # set a style
+    def style(s):
+        if s | length == 1 then "__yq_style_" + s + "__" + (. | style) # remove previous styles
+        else error("Only valid symbols are \", ', |, >, _")
+        end;
+
+
+This allows to simpify the above example to::
+
+    yq -y -z '.field1 |= style("|")' input.yaml
+
+
 XML support
 -----------
 ``yq`` also supports XML. The ``yq`` package installs an executable, ``xq``, which

yq/__init__.py

@@ -192,6 +192,7 @@ def yq(
     expand_aliases=True,
     max_expansion_factor=1024,
     yaml_output_grammar_version="1.1",
+    yaml_string_styles=False,
     jq_args=frozenset(),
     exit_func=None,
 ):
@@ -268,6 +269,7 @@ def yq(
                     use_annotations=use_annotations,
                     indentless=indentless_lists,
                     grammar_version=yaml_output_grammar_version,
+                    use_string_styles=yaml_string_styles
                 )
                 yaml.dump_all(
                     decode_docs(jq_out, json_decoder),

yq/dumper.py

@@ -26,7 +26,27 @@ def ignore_aliases(self, data):
 yaml_item_annotation_re = re.compile(r"^__yq_(?P<type>tag|style)_(?P<key>\d+)_(?P<value>.+)__$")
 
 
-def get_dumper(use_annotations=False, indentless=False, grammar_version="1.1"):
+def extractStringStyle(v):
+    if v.value.startswith("__yq_style_|__"):
+        v.value = v.value[14:]
+        v.style = '|'
+    elif v.value.startswith("__yq_style_>__"):
+        v.value = v.value[14:]
+        v.style = '>'
+    elif v.value.startswith("__yq_style_'__"):
+        v.value = v.value[14:]
+        v.style = '\''
+    elif v.value.startswith("__yq_style_\"__"):
+        v.value = v.value[14:]
+        v.style = '"'
+    elif v.value.startswith("__yq_style____"):
+        v.value = v.value[14:]
+        v.style = None
+
+    return v
+
+
+def get_dumper(use_annotations=False, indentless=False, grammar_version="1.1", use_string_styles=False):
     # if not (use_annotations or indentless):
     #     return default_dumper
 
@@ -55,6 +75,7 @@ def represent_dict(dumper, data):
                         v.flow_style = True
                 if hashed_key in custom_tags:
                     v.tag = custom_tags[hashed_key]
+
         return mapping
 
     def represent_list(dumper, data):
@@ -79,10 +100,17 @@ def represent_list(dumper, data):
                         v.flow_style = True
                 if str(i) in custom_tags:
                     v.tag = custom_tags[str(i)]
+
         return sequence
 
+    def represent_str(dumper, data):
+        scalar = dumper.represent_scalar("tag:yaml.org,2002:str", value=data)
+        return extractStringStyle(scalar)
+
     dumper = OrderedIndentlessDumper if indentless else OrderedDumper
     dumper.add_representer(dict, represent_dict)
     dumper.add_representer(list, represent_list)
+    if use_string_styles:
+        dumper.add_representer(str, represent_str)
     set_yaml_grammar(dumper, grammar_version=grammar_version)
     return dumper

yq/parser.py

@@ -100,6 +100,12 @@ def get_parser(program_name, description):
     parser.add_argument(
         "--yaml-output-grammar-version", "--yml-out-ver", choices=["1.1", "1.2"], default="1.1", help=grammar_help
     )
+    parser.add_argument(
+        "--yaml-string-styles",
+        "--yml-string-styles",
+        "-z",
+        action="store_true",
+        help="Allows special strings to control style of strings (only valid in combination with -y or -Y)")
     parser.add_argument("--width", "-w", type=int, help=width_help)
     parser.add_argument("--indentless-lists", "--indentless", action="store_true", help=indentless_help)
     parser.add_argument("--explicit-start", action="store_true", help=explicit_start_help)